Benzi: compiler-backed coding agent hits 78.2% on SWE-bench Verified for $37
Benzi parses your repo with tree-sitter into a resolved map of symbols, call edges, data flow, and inheritance, then has the model query it through ~36 structured tools instead of reading raw files; it ships as a VS Code extension, a pip install benzi package, and an MCP server. Its authors report 391/500 on SWE-bench Verified with DeepSeek v4-flash at pass@1 for $37.33 total, a self-run result that includes a review pass, not just the index.